文献类型：会议论文

英文题名：Fault feature selection based on PSO/TS and its application in chemical process fault diagnosis

作者：Wang, L; Yu, JS

机构：[1]E China Univ Sci & Technol, Res Inst Automat, Shanghai 200237, Peoples R China

会议论文集：4th International Conference on Engineering Applications and Computational Algorithms

会议日期：JUL 27-29, 2005

会议地点：Univ Guelph, Guelph, CANADA

主办单位：Univ Guelph

语种：英文

摘要：In large scale industry system, especially in chemical process industry, large amounts of variables are monitored. When all variables are collected for fault diagnosis, it results in poor fault classification because there are too many irrelevant variables, which also increase the dimensions of data. A novel optimization algorithm, based on Particle Swarm Optimization (PSO) and Tabu search (TS) combined with Support Vector Machine (SVM), is proposed to select the fault feature variables for fault diagnosis. The simulations on Tennessee Eastman process (TEP) show the PSO/TS algorithm can effectively escape form local optima to find the globe optimal value comparing with initial PSO. And with fault feature selection, more satisfied performance of fault diagnosis achieves.